{"id":"https://openalex.org/W4387969113","doi":"https://doi.org/10.1145/3581783.3611970","title":"Object Segmentation by Mining Cross-Modal Semantics","display_name":"Object Segmentation by Mining Cross-Modal Semantics","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969113","doi":"https://doi.org/10.1145/3581783.3611970"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102023784","display_name":"Zongwei Wu","orcid":"https://orcid.org/0000-0001-7772-4152"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zongwei Wu","raw_affiliation_strings":["Computer Vision Lab, CAIDAS & IFI, University of Wurzburg, Wurzburg, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Vision Lab, CAIDAS & IFI, University of Wurzburg, Wurzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102715144","display_name":"Jingjing Wang","orcid":"https://orcid.org/0009-0005-3953-6472"},"institutions":[{"id":"https://openalex.org/I184681353","display_name":"Anhui University of Science and Technology","ror":"https://ror.org/00q9atg80","country_code":"CN","type":"education","lineage":["https://openalex.org/I184681353"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Wang","raw_affiliation_strings":["Anhui University of Science and Technology, Huainan, China"],"affiliations":[{"raw_affiliation_string":"Anhui University of Science and Technology, Huainan, China","institution_ids":["https://openalex.org/I184681353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003100135","display_name":"Zhuyun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I177064439","display_name":"Universit\u00e9 de Bourgogne","ror":"https://ror.org/03k1bsr36","country_code":"FR","type":"education","lineage":["https://openalex.org/I177064439"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zhuyun Zhou","raw_affiliation_strings":["University of Burgundy, CNRS, ICB, Dijon, France"],"affiliations":[{"raw_affiliation_string":"University of Burgundy, CNRS, ICB, Dijon, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I177064439"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086771628","display_name":"Zhaochong An","orcid":"https://orcid.org/0009-0007-5985-7470"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zhaochong An","raw_affiliation_strings":["CVL, ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"CVL, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000581688","display_name":"Qiuping Jiang","orcid":"https://orcid.org/0000-0002-6025-9343"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuping Jiang","raw_affiliation_strings":["Ningbo University, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088809198","display_name":"C\u00e9dric Demonceaux","orcid":"https://orcid.org/0000-0001-6916-1273"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I177064439","display_name":"Universit\u00e9 de Bourgogne","ror":"https://ror.org/03k1bsr36","country_code":"FR","type":"education","lineage":["https://openalex.org/I177064439"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C\u00e9dric Demonceaux","raw_affiliation_strings":["University of Burgundy, CNRS, ICB, Dijon, France"],"affiliations":[{"raw_affiliation_string":"University of Burgundy, CNRS, ICB, Dijon, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I177064439"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010215983","display_name":"Guolei Sun","orcid":"https://orcid.org/0000-0001-8667-9656"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Guolei Sun","raw_affiliation_strings":["CVL, ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"CVL, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052236177","display_name":"Radu Timofte","orcid":"https://orcid.org/0000-0002-1478-0402"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Radu Timofte","raw_affiliation_strings":["Computer Vision Lab, CAIDAS and IFI, University of Wurzburg, Wurzburg, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Vision Lab, CAIDAS and IFI, University of Wurzburg, Wurzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102023784"],"corresponding_institution_ids":["https://openalex.org/I25974101"],"apc_list":null,"apc_paid":null,"fwci":3.8833,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95124342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3455","last_page":"3464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7981741428375244},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6202622652053833},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5732240080833435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5340249538421631},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5225203037261963},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5189394950866699},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4690917730331421},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44326385855674744},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44018325209617615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4284965991973877},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33083295822143555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16126373410224915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981741428375244},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6202622652053833},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5732240080833435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340249538421631},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5225203037261963},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5189394950866699},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4690917730331421},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44326385855674744},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44018325209617615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4284965991973877},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33083295822143555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16126373410224915},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320327269","display_name":"Conseil r\u00e9gional de Bourgogne-Franche-Comt\u00e9","ror":"https://ror.org/04t9bwz39"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W20683899","https://openalex.org/W1976409045","https://openalex.org/W1993713494","https://openalex.org/W2194775991","https://openalex.org/W2501607496","https://openalex.org/W2546134707","https://openalex.org/W2560023338","https://openalex.org/W2799213142","https://openalex.org/W2887486131","https://openalex.org/W2901017177","https://openalex.org/W2943545929","https://openalex.org/W2945809413","https://openalex.org/W2955639361","https://openalex.org/W2957414648","https://openalex.org/W2963163009","https://openalex.org/W2963177347","https://openalex.org/W2963676935","https://openalex.org/W2968997458","https://openalex.org/W3034684132","https://openalex.org/W3035284915","https://openalex.org/W3035502324","https://openalex.org/W3039479109","https://openalex.org/W3047800102","https://openalex.org/W3081167590","https://openalex.org/W3093213431","https://openalex.org/W3134912427","https://openalex.org/W3135874576","https://openalex.org/W3159018159","https://openalex.org/W3171757599","https://openalex.org/W3173882198","https://openalex.org/W3175515048","https://openalex.org/W3176152216","https://openalex.org/W3177040887","https://openalex.org/W3179443972","https://openalex.org/W3179923621","https://openalex.org/W3185043317","https://openalex.org/W3197308605","https://openalex.org/W3204197760","https://openalex.org/W3206198586","https://openalex.org/W3207668590","https://openalex.org/W3207804100","https://openalex.org/W3211246039","https://openalex.org/W3212645988","https://openalex.org/W4206715824","https://openalex.org/W4214520160","https://openalex.org/W4214680709","https://openalex.org/W4214696292","https://openalex.org/W4224238525","https://openalex.org/W4226017195","https://openalex.org/W4285058230","https://openalex.org/W4285161446","https://openalex.org/W4285163934","https://openalex.org/W4287164258","https://openalex.org/W4288773267","https://openalex.org/W4293731746","https://openalex.org/W4295424676","https://openalex.org/W4296031724","https://openalex.org/W4304014335","https://openalex.org/W4304098552","https://openalex.org/W4307771365","https://openalex.org/W4312258849","https://openalex.org/W4312334320","https://openalex.org/W4312366074","https://openalex.org/W4312612915","https://openalex.org/W4312707458","https://openalex.org/W4319866558","https://openalex.org/W4319879007","https://openalex.org/W4327807853","https://openalex.org/W4362496243","https://openalex.org/W4386076039","https://openalex.org/W4386581228","https://openalex.org/W6600075554","https://openalex.org/W6603398137","https://openalex.org/W6604662147","https://openalex.org/W6605363982","https://openalex.org/W6810421512"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W2542937328","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W4360952157","https://openalex.org/W4220731478","https://openalex.org/W2069409835","https://openalex.org/W3112772842"],"abstract_inverted_index":{"Multi-sensor":[0],"clues":[1],"have":[2],"shown":[3],"promise":[4],"for":[5],"object":[6,189],"segmentation,":[7,190],"but":[8],"inherent":[9],"noise":[10],"in":[11,20,68,194],"each":[12],"sensor,":[13],"as":[14,16],"well":[15],"the":[17,24,37,42,50,54,65,71,75,102,105,110,119,124,131,134,141,147,158],"calibration":[18],"error":[19],"practice,":[21],"may":[22],"bias":[23],"segmentation":[25],"accuracy.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,79,153],"propose":[31,80],"a":[32,81],"novel":[33,82],"approach":[34],"by":[35,122],"mining":[36],"Cross-Modal":[38],"Semantics":[39],"to":[40,117,161],"guide":[41],"fusion":[43,91],"and":[44,74,97,112,115,127,144,180,187,199],"decoding":[45,159],"of":[46,52,87,196],"multimodal":[47,66],"features,":[48],"with":[49,175],"aim":[51],"controlling":[53],"modal":[55,120],"contribution":[56,121],"based":[57],"on":[58,172,181],"relative":[59],"entropy.":[60],"We":[61],"explore":[62],"semantics":[63],"among":[64],"inputs":[67],"two":[69,182],"aspects:":[70],"modality-shared":[72],"consistency":[73,156],"modality-specific":[76],"variation.":[77],"Specifically,":[78],"network,":[83],"termed":[84],"XMSNet,":[85],"consisting":[86],"(1)":[88],"all-round":[89],"attentive":[90],"(AF),":[92],"(2)":[93],"coarse-to-fine":[94],"decoder":[95],"(CFD),":[96],"(3)":[98],"cross-layer":[99],"self-supervision.":[100],"On":[101,133],"one":[103],"hand,":[104,136],"AF":[106],"block":[107],"explicitly":[108],"dissociates":[109],"shared":[111,142],"specific":[113],"representation":[114],"learns":[116],"weight":[118],"adjusting":[123],"proportion,":[125],"region,":[126],"pattern,":[128],"depending":[129],"upon":[130],"quality.":[132],"other":[135],"our":[137,192],"CFD":[138],"initially":[139],"decodes":[140],"feature":[143,168],"then":[145],"refines":[146],"output":[148],"through":[149],"specificity-aware":[150],"querying.":[151],"Further,":[152],"enforce":[154],"semantic":[155],"across":[157,164],"layers":[160],"enable":[162],"interaction":[163],"network":[165],"hierarchies,":[166],"improving":[167],"discriminability.":[169],"Exhaustive":[170],"comparison":[171],"eleven":[173],"datasets":[174],"depth":[176],"or":[177],"thermal":[178],"clues,":[179],"challenging":[183],"tasks,":[184],"namely":[185],"salient":[186],"camouflage":[188],"validate":[191],"effectiveness":[193],"terms":[195],"both":[197],"performance":[198],"robustness.":[200],"The":[201],"source":[202],"code":[203],"is":[204],"publicly":[205],"available":[206],"at":[207],"https://github.com/Zongwei97/XMSNet.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}